© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84113
    Prev
    Next
    INDEX
    Explanations

    let alone

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on occurrences of the word “let.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    సం
    -0.84
    ]==
    -0.82
     nincs
    -0.81
    してみて
    -0.80
     október
    -0.79
    obby
    -0.79
     lộc
    -0.77
    粲
    -0.77
    quée
    -0.77
    лений
    -0.76
    POSITIVE LOGITS
     alone
    9.38
    alone
    6.44
     Alone
    5.44
    Alone
    5.19
     ALONE
    4.88
     allein
    4.78
     alleine
    4.28
     seul
    3.72
     alene
    3.56
     seule
    3.55
    Activations Density 0.248%

    No Known Activations